公开(公告)号：US07366635B1

公开(公告)日：2008-04-29

申请号：US11006342

申请日：2004-12-06

Applicant: Niraj Gupta ,  Martin E. Newell ,  Peter F. Ullmann

Inventor： Niraj Gupta ,  Martin E. Newell ,  Peter F. Ullmann

IPC: G06F11/00

CPC classification number: G06T11/001

Abstract: Methods, systems, and apparatus, including computer program products, for calculating or applying a gradient over a region in a multi-dimensional space. A boundary defines the shape of the region. A gradient specifies a value transition between a starting position and an ending position. The following actions are performed to calculate a gradient value at any point in the selected region: determining an interpolation vector extending from an effective origin included in the starting position through the point to the ending position and defining a gradient value for the point according to the gradient and based on the position of the point along the interpolation vector relative to the effective origin and an intersection point where the interpolation vector meets the boundary.

Abstract translation: 包括用于在多维空间中的区域上计算或应用梯度的计算机程序产品的方法，系统和装置。 边界定义区域的形状。 梯度指定起始位置和结束位置之间的值转换。 执行以下动作以计算所选区域中的任何点处的梯度值：确定从包括在开始位置的有效原点通过该点延伸到终止位置的插值向量，并且根据该点定义该点的梯度值 并且基于相对于有效原点的插值向量的点的位置和插值向量与边界相遇的交点。

公开(公告)号：US20150125085A1

公开(公告)日：2015-05-07

申请号：US14071006

申请日：2013-11-04

Applicant: Niraj Gupta

Inventor： Niraj Gupta

IPC: H04N19/103

CPC classification number: H04N19/103 ,  G06T1/60 ,  G06T9/00 ,  H04N19/423 ,  H04N19/436

Abstract: Techniques related to integral image coding are described herein.

Abstract translation: 本文描述了与整体图像编码相关的技术。

公开(公告)号：US20140379993A1

公开(公告)日：2014-12-25

申请号：US13926328

申请日：2013-06-25

Applicant: Niraj Gupta ,  Hong Jiang

Inventor： Niraj Gupta ,  Hong Jiang

IPC: G06F12/08 ,  G06F12/12

CPC classification number: G06F12/0837 ,  G06F12/0808 ,  G06F2212/302

Abstract: Methods and systems may provide for receiving, at a graphics processor, a workload from a host processor and using a kernel on the graphics processor to issue a thread group for execution of the workload on the graphics processor. Additionally, one or more coherency messages may be initiated, by the graphics processor, in response to a thread-related condition of one or more caches on the graphics processor. In one example, the thread-related condition is associated with the execution of the workload on the graphics processor and indicates that the one or more caches on the graphics processor are not coherent with a system memory associated with the host processor.

Abstract translation: 方法和系统可以提供在图形处理器处接收来自主机处理器的工作负载并且使用图形处理器上的内核来发布用于在图形处理器上执行工作负载的线程组。 另外，响应于图形处理器上的一个或多个高速缓存的线程相关状况，图形处理器可以启动一个或多个一致性消息。 在一个示例中，线程相关条件与图形处理器上的工作负载的执行相关联，并且指示图形处理器上的一个或多个高速缓存与与主机处理器相关联的系统存储器不一致。

公开(公告)号：US20140104285A1

公开(公告)日：2014-04-17

申请号：US13651854

申请日：2012-10-15

Applicant: Alon Gluska ,  Niraj Gupta ,  Mostafa Hagog ,  Dror Reif

Inventor： Alon Gluska ,  Niraj Gupta ,  Mostafa Hagog ,  Dror Reif

IPC: G06F15/16 ,  G06T1/00

CPC classification number: G06T1/20

Abstract: Flood-fill techniques and architecture are disclosed. In accordance with one embodiment, the architecture comprises a hardware primitive with a software interface which collectively allow for both data-based and task-based parallelism in executing a flood-fill process. The hardware primitive is defined to do the flood-fill function and is scalable and may be implemented with a bitwise definition that can be tuned to meet power/performance targets, in some embodiments. In executing a flood-fill operation, and in accordance with an example embodiment, the software interface produces parallel threads and issues them to processing elements, such that each of the threads can run independently until done. Each processing element in turn accesses a flood-fill hardware primitive, each of which is configured to flood a seed inside an N×M image block. In some cases, processing element commands to the flood-fill hardware primitive(s) can be queued and acted upon pursuant to an arbitration scheme.

Abstract translation: 洪水填充技术和结构被公开。 根据一个实施例，该架构包括具有软件接口的硬件原语，该软件接口在执行洪水填充处理时共同允许基于数据和基于任务的并行性。 硬件原语被定义为执行洪水填充功能并且是可扩展的，并且可以在一些实施例中以可以调整以满足功率/性能目标的按位定义来实现。 在执行洪水填充操作时，并且根据示例性实施例，软件接口产生并行线程并将其发布到处理元件，使得每个线程可以独立运行直到完成。 每个处理元件依次访问洪水填充硬件图元，其中的每一个被配置为在N×M图像块内泛滥种子。 在某些情况下，根据仲裁方案，可以对洪水填充硬件原语的处理单元命令进行排队和执行。

公开(公告)号：US06493119B1

公开(公告)日：2002-12-10

申请号：US09648518

申请日：2000-08-25

Applicant: Chien-Yu Kuo ,  Niraj Gupta ,  Ronald Garrison

Inventor： Chien-Yu Kuo ,  Niraj Gupta ,  Ronald Garrison

IPC: H04B1020

CPC classification number: H04B10/1149 ,  H04B10/504 ,  H04B10/564 ,  H04B10/572 ,  H04J14/0221 ,  H04Q11/0005 ,  H04Q2011/0016 ,  H04Q2011/0018 ,  H04Q2011/0024

Abstract: A network switch connecting N input optical fibers and N output optical fibers, each optical fiber carrying M wavelength channels. The network switch has a control unit, a plurality of demultiplexers connected to the input output optical fibers, a plurality of tunable channel units, a switch fabric and a plurality of combiners connected to the output optical fibers. The demultiplexers and tunable channel units provide the wavelength routing function and the switch fabric, which has M×N2 switch points, switches signals from input optical fiber to output fiber so that the switch can switch signals from one wavelength channel to another and from one input optical fiber to one or more output optical fibers of the optical network. The switch fabric is formed from a plurality of switch modules, one switch module for each incoming wavelength channel. The switch modules are also formed from partitionable arrangements of switch elements and combiners so that the switch fabric and switch can be scaled up and reconfigured on an “as needed” basis.

Abstract translation: 一个网络交换机连接N个输入​​光纤和N个输出光纤，每个光纤承载M个波长信道。 网络交换机具有控制单元，连接到输入输出光纤的多个解复用器，多个可调谐通道单元，交换结构和连接到输出光纤的多个组合器。 解复用器和可调谐信道单元提供波长路由功能，具有MxN2切换点的交换结构将信号从输入光纤切换到输出光纤，使得交换机可以将信号从一个波长信道切换到另一个波长信道，并从一个输入光纤 到光网络的一个或多个输出光纤。 交换结构由多个开关模块形成，一个用于每个输入波长通道的开关模块。 交换机模块也由开关元件和组合器的可分割布置形成，使得交换结构和交换机可以在“根据需要”的基础上进行放大和重新配置。

公开(公告)号：US09398297B2

公开(公告)日：2016-07-19

申请号：US14071006

申请日：2013-11-04

Applicant: Niraj Gupta

Inventor： Niraj Gupta

IPC: G06T1/60 ,  G06T9/00 ,  H04N19/103 ,  H04N19/423 ,  H04N19/436

CPC classification number: H04N19/103 ,  G06T1/60 ,  G06T9/00 ,  H04N19/423 ,  H04N19/436

Abstract: Techniques related to integral image coding are described herein.

Abstract translation: 本文描述了与整体图像编码相关的技术。

公开(公告)号：US20140222884A1

公开(公告)日：2014-08-07

申请号：US13759274

申请日：2013-02-05

Applicant: Niraj Gupta

Inventor： Niraj Gupta

IPC: G06F7/52

CPC classification number: G06F7/535 ,  G06F2207/5354 ,  G06F2207/5356

Abstract: Systems, apparatus and methods are described related to optimizing fixed point divide.

Abstract translation: 描述了优化固定点分割的系统，装置和方法。

公开(公告)号：US20140119657A1

公开(公告)日：2014-05-01

申请号：US13666913

申请日：2012-11-01

Applicant: Niraj Gupta ,  Oren Agam ,  Benny Eitan ,  Mostafa Hagog

Inventor： Niraj Gupta ,  Oren Agam ,  Benny Eitan ,  Mostafa Hagog

IPC: G06K9/36

CPC classification number: G06K9/4638 ,  G06T7/11 ,  G06T7/187 ,  G06T2200/28

Abstract: An apparatus may include a memory, a processor circuit, and a connected component labeling module. The connected component labeling module may be operative of the processor circuit to determine one or more connected components during reading of an image comprising a multiplicity of pixels from the memory, assign a label to a plurality of pixels of the multiplicity of pixels, generate one or more label connections for a respective one or more labels, each label connection linking a higher label to a lowest label for the same connected component, and write to the memory for each label of the one or more labels a lowest label as defined by the label connection for the each label after a label is assigned to each pixel.

Abstract translation: 装置可以包括存储器，处理器电路和连接的部件标签模块。 连接的组件标注模块可操作于处理器电路，以在从存储器读取包括多个像素的图像的读取期间确定一个或多个连接的组件，将标签分配给多个像素的多个像素，生成一个或多个 针对相应的一个或多个标签的更多标签连接，每个标签连接将较高标签链接到相同连接部件的最低标签，并且向该存储器写入一个或多个标签的每个标签，该标签由标签定义 将标签分配给每个像素后，每个标签的连接。

公开(公告)号：US06870954B1

公开(公告)日：2005-03-22

申请号：US09826488

申请日：2001-04-04

Applicant: Niraj Gupta

Inventor： Niraj Gupta

IPC: G06K9/00 ,  G06T11/00 ,  G06T11/20

CPC classification number: G06T11/40

Abstract: Computer-implemented methods and computer program apparatus, for implementing techniques for shading selected regions of an image. These include receiving an input selecting a region to be filled, receiving an input defining a gradient specifying a color transition to be applied between a starting position and an ending position, and applying the gradient between the starting position and the ending position to assign, based on the shape of the selected region, a color for each of a plurality of points located inside an outline defining the region's shape. In preferred embodiments, the gradient is applied by identifying, for each point in the selected region, a color interpolation vector extending from the starting position through the point to the ending position and intersecting the outline at one or more intersection points, and assigning a color for the point based on its position along the color interpolation vector.

Abstract translation: 计算机实现的方法和计算机程序设备，用于实现用于遮蔽图像的选定区域的技术。 这些包括接收选择要填充的区域的输入，接收定义指定要在起始位置和结束位置之间施加的颜色转变的渐变的输入，以及在开始位置和结束位置之间应用渐变以分配 在所选择的区域的形状上，对于位于限定区域的形状的轮廓内的多个点中的每一个点的颜色。 在优选实施例中，通过针对所选择的区域中的每个点识别从起始位置到点到结束位置并在一个或多个交叉点处与轮廓相交的颜色插值向量来应用梯度，并且分配颜色 基于其沿颜色插值向量的位置的点。

公开(公告)号：US06774907B1

公开(公告)日：2004-08-10

申请号：US09467307

申请日：1999-12-17

Applicant: Niraj Gupta

Inventor： Niraj Gupta

IPC: G09G502

CPC classification number: G06T11/001

Abstract: A computer-implemented method for generating a graphic fill includes selecting a tint curve and a tint vector for a graphical object; and applying a tint transform to the fill of the graphical object.

Abstract translation: 用于生成图形填充的计算机实现的方法包括为图形对象选择色调曲线和色调矢量; 以及对图形对象的填充应用色调变换。